May 6, 2019

2827 words 14 mins read

Paper Group ANR 275

Evaluating the Performance of Offensive Linemen in the NFL. Combinatorially Generated Piecewise Activation Functions. Comparison-based Image Quality Assessment for Parameter Selection. Automated Visual Fin Identification of Individual Great White Sharks. Clustering and Community Detection with Imbalanced Clusters. On model architecture for a childr …

Evaluating the Performance of Offensive Linemen in the NFL


Title	Evaluating the Performance of Offensive Linemen in the NFL
Authors	Nikhil Byanna, Diego Klabjan
Abstract	How does one objectively measure the performance of an individual offensive lineman in the NFL? The existing literature proposes various measures that rely on subjective assessments of game film, but has yet to develop an objective methodology to evaluate performance. Using a variety of statistics related to an offensive lineman’s performance, we develop a framework to objectively analyze the overall performance of an individual offensive lineman and determine specific linemen who are overvalued or undervalued relative to their salary. We identify eight players across the 2013-2014 and 2014-2015 NFL seasons that are considered to be overvalued or undervalued and corroborate the results with existing metrics that are based on subjective evaluation. To the best of our knowledge, the techniques set forth in this work have not been utilized in previous works to evaluate the performance of NFL players at any position, including offensive linemen.
Tasks
Published	2016-03-24
URL	http://arxiv.org/abs/1603.07593v2
PDF	http://arxiv.org/pdf/1603.07593v2.pdf
PWC	https://paperswithcode.com/paper/evaluating-the-performance-of-offensive
Repo
Framework

Combinatorially Generated Piecewise Activation Functions


Title	Combinatorially Generated Piecewise Activation Functions
Authors	Justin Chen
Abstract	In the neuroevolution literature, research has primarily focused on evolving the number of nodes, connections, and weights in artificial neural networks. Few attempts have been made to evolve activation functions. Research in evolving activation functions has mainly focused on evolving function parameters, and developing heterogeneous networks by selecting from a fixed pool of activation functions. This paper introduces a novel technique for evolving heterogeneous artificial neural networks through combinatorially generating piecewise activation functions to enhance expressive power. I demonstrate this technique on NeuroEvolution of Augmenting Topologies using ArcTan and Sigmoid, and show that it outperforms the original algorithm on non-Markovian double pole balancing. This technique expands the landscape of unconventional activation functions by demonstrating that they are competitive with canonical choices, and introduces a purview for further exploration of automatic model selection for artificial neural networks.
Tasks	Model Selection
Published	2016-05-17
URL	http://arxiv.org/abs/1605.05216v1
PDF	http://arxiv.org/pdf/1605.05216v1.pdf
PWC	https://paperswithcode.com/paper/combinatorially-generated-piecewise
Repo
Framework

Comparison-based Image Quality Assessment for Parameter Selection


Title	Comparison-based Image Quality Assessment for Parameter Selection
Authors	Haoyi Liang, Daniel S. Weller
Abstract	Image quality assessment (IQA) is traditionally classified into full-reference (FR) IQA and no-reference (NR) IQA according to whether the original image is required. Although NR-IQA is widely used in practical applications, room for improvement still remains because of the lack of the reference image. Inspired by the fact that in many applications, such as parameter selection, a series of distorted images are available, the authors propose a novel comparison-based image quality assessment (C-IQA) method. The new comparison-based framework parallels FR-IQA by requiring two input images, and resembles NR-IQA by not using the original image. As a result, the new comparison-based approach has more application scenarios than FR-IQA does, and takes greater advantage of the accessible information than the traditional single-input NR-IQA does. Further, C-IQA is compared with other state-of-the-art NR-IQA methods on two widely used IQA databases. Experimental results show that C-IQA outperforms the other NR-IQA methods for parameter selection, and the parameter trimming framework combined with C-IQA saves the computation of iterative image reconstruction up to 80%.
Tasks	Image Quality Assessment, Image Reconstruction
Published	2016-01-18
URL	http://arxiv.org/abs/1601.04619v1
PDF	http://arxiv.org/pdf/1601.04619v1.pdf
PWC	https://paperswithcode.com/paper/comparison-based-image-quality-assessment-for
Repo
Framework

Automated Visual Fin Identification of Individual Great White Sharks


Title	Automated Visual Fin Identification of Individual Great White Sharks
Authors	Benjamin Hughes, Tilo Burghardt
Abstract	This paper discusses the automated visual identification of individual great white sharks from dorsal fin imagery. We propose a computer vision photo ID system and report recognition results over a database of thousands of unconstrained fin images. To the best of our knowledge this line of work establishes the first fully automated contour-based visual ID system in the field of animal biometrics. The approach put forward appreciates shark fins as textureless, flexible and partially occluded objects with an individually characteristic shape. In order to recover animal identities from an image we first introduce an open contour stroke model, which extends multi-scale region segmentation to achieve robust fin detection. Secondly, we show that combinatorial, scale-space selective fingerprinting can successfully encode fin individuality. We then measure the species-specific distribution of visual individuality along the fin contour via an embedding into a global `fin space’. Exploiting this domain, we finally propose a non-linear model for individual animal recognition and combine all approaches into a fine-grained multi-instance framework. We provide a system evaluation, compare results to prior work, and report performance and properties in detail. \|
Tasks
Published	2016-09-20
URL	http://arxiv.org/abs/1609.06323v2
PDF	http://arxiv.org/pdf/1609.06323v2.pdf
PWC	https://paperswithcode.com/paper/automated-visual-fin-identification-of
Repo
Framework

Clustering and Community Detection with Imbalanced Clusters


Title	Clustering and Community Detection with Imbalanced Clusters
Authors	Cem Aksoylar, Jing Qian, Venkatesh Saligrama
Abstract	Spectral clustering methods which are frequently used in clustering and community detection applications are sensitive to the specific graph constructions particularly when imbalanced clusters are present. We show that ratio cut (RCut) or normalized cut (NCut) objectives are not tailored to imbalanced cluster sizes since they tend to emphasize cut sizes over cut values. We propose a graph partitioning problem that seeks minimum cut partitions under minimum size constraints on partitions to deal with imbalanced cluster sizes. Our approach parameterizes a family of graphs by adaptively modulating node degrees on a fixed node set, yielding a set of parameter dependent cuts reflecting varying levels of imbalance. The solution to our problem is then obtained by optimizing over these parameters. We present rigorous limit cut analysis results to justify our approach and demonstrate the superiority of our method through experiments on synthetic and real datasets for data clustering, semi-supervised learning and community detection.
Tasks	Community Detection, graph partitioning
Published	2016-08-26
URL	http://arxiv.org/abs/1608.07605v1
PDF	http://arxiv.org/pdf/1608.07605v1.pdf
PWC	https://paperswithcode.com/paper/clustering-and-community-detection-with
Repo
Framework

On model architecture for a children’s speech recognition interactive dialog system


Title	On model architecture for a children’s speech recognition interactive dialog system
Authors	Radoslava Kraleva, Velin Kralev
Abstract	This report presents a general model of the architecture of information systems for the speech recognition of children. It presents a model of the speech data stream and how it works. The result of these studies and presented veins architectural model shows that research needs to be focused on acoustic-phonetic modeling in order to improve the quality of children’s speech recognition and the sustainability of the systems to noise and changes in transmission environment. Another important aspect is the development of more accurate algorithms for modeling of spontaneous child speech.
Tasks	Speech Recognition
Published	2016-05-25
URL	http://arxiv.org/abs/1605.07733v1
PDF	http://arxiv.org/pdf/1605.07733v1.pdf
PWC	https://paperswithcode.com/paper/on-model-architecture-for-a-childrens-speech
Repo
Framework

Towards an Automated Requirements-driven Development of Smart Cyber-Physical Systems


Title	Towards an Automated Requirements-driven Development of Smart Cyber-Physical Systems
Authors	Jiri Vinarek, Petr Hnetynka
Abstract	The Invariant Refinement Method for Self Adaptation (IRM-SA) is a design method targeting development of smart Cyber-Physical Systems (sCPS). It allows for a systematic translation of the system requirements into the system architecture expressed as an ensemble-based component system (EBCS). However, since the requirements are captured using natural language, there exists the danger of their misinterpretation due to natural language requirements’ ambiguity, which could eventually lead to design errors. Thus, automation and validation of the design process is desirable. In this paper, we (i) analyze the translation process of natural language requirements into the IRM-SA model, (ii) identify individual steps that can be automated and/or validated using natural language processing techniques, and (iii) propose suitable methods.
Tasks
Published	2016-03-29
URL	http://arxiv.org/abs/1603.08636v1
PDF	http://arxiv.org/pdf/1603.08636v1.pdf
PWC	https://paperswithcode.com/paper/towards-an-automated-requirements-driven
Repo
Framework

Networked Intelligence: Towards Autonomous Cyber Physical Systems


Title	Networked Intelligence: Towards Autonomous Cyber Physical Systems
Authors	Andre Karpistsenko
Abstract	Developing intelligent systems requires combining results from both industry and academia. In this report you find an overview of relevant research fields and industrially applicable technologies for building very large scale cyber physical systems. A concept architecture is used to illustrate how existing pieces may fit together, and the maturity of the subsystems is estimated. The goal is to structure the developments and the challenge of machine intelligence for Consumer and Industrial Internet technologists, cyber physical systems researchers and people interested in the convergence of data & Internet of Things. It can be used for planning developments of intelligent systems.
Tasks
Published	2016-06-13
URL	http://arxiv.org/abs/1606.04087v6
PDF	http://arxiv.org/pdf/1606.04087v6.pdf
PWC	https://paperswithcode.com/paper/networked-intelligence-towards-autonomous
Repo
Framework

Using a Deep Reinforcement Learning Agent for Traffic Signal Control


Title	Using a Deep Reinforcement Learning Agent for Traffic Signal Control
Authors	Wade Genders, Saiedeh Razavi
Abstract	Ensuring transportation systems are efficient is a priority for modern society. Technological advances have made it possible for transportation systems to collect large volumes of varied data on an unprecedented scale. We propose a traffic signal control system which takes advantage of this new, high quality data, with minimal abstraction compared to other proposed systems. We apply modern deep reinforcement learning methods to build a truly adaptive traffic signal control agent in the traffic microsimulator SUMO. We propose a new state space, the discrete traffic state encoding, which is information dense. The discrete traffic state encoding is used as input to a deep convolutional neural network, trained using Q-learning with experience replay. Our agent was compared against a one hidden layer neural network traffic signal control agent and reduces average cumulative delay by 82%, average queue length by 66% and average travel time by 20%.
Tasks	Q-Learning
Published	2016-11-03
URL	http://arxiv.org/abs/1611.01142v1
PDF	http://arxiv.org/pdf/1611.01142v1.pdf
PWC	https://paperswithcode.com/paper/using-a-deep-reinforcement-learning-agent-for
Repo
Framework

Intelligent information extraction based on artificial neural network


Title	Intelligent information extraction based on artificial neural network
Authors	Ahlam Ansari, Moonish Maknojia, Altamash Shaikh
Abstract	Question Answering System (QAS) is used for information retrieval and natural language processing (NLP) to reduce human effort. There are numerous QAS based on the user documents present today, but they all are limited to providing objective answers and process simple questions only. Complex questions cannot be answered by the existing QAS, as they require interpretation of the current and old data as well as the question asked by the user. The above limitations can be overcome by using deep cases and neural network. Hence we propose a modified QAS in which we create a deep artificial neural network with associative memory from text documents. The modified QAS processes the contents of the text document provided to it and find the answer to even complex questions in the documents.
Tasks	Information Retrieval, Question Answering
Published	2016-04-11
URL	http://arxiv.org/abs/1612.09327v1
PDF	http://arxiv.org/pdf/1612.09327v1.pdf
PWC	https://paperswithcode.com/paper/intelligent-information-extraction-based-on
Repo
Framework

Robust Deep Appearance Models


Title	Robust Deep Appearance Models
Authors	Kha Gia Quach, Chi Nhan Duong, Khoa Luu, Tien D. Bui
Abstract	This paper presents a novel Robust Deep Appearance Models to learn the non-linear correlation between shape and texture of face images. In this approach, two crucial components of face images, i.e. shape and texture, are represented by Deep Boltzmann Machines and Robust Deep Boltzmann Machines (RDBM), respectively. The RDBM, an alternative form of Robust Boltzmann Machines, can separate corrupted/occluded pixels in the texture modeling to achieve better reconstruction results. The two models are connected by Restricted Boltzmann Machines at the top layer to jointly learn and capture the variations of both facial shapes and appearances. This paper also introduces new fitting algorithms with occlusion awareness through the mask obtained from the RDBM reconstruction. The proposed approach is evaluated in various applications by using challenging face datasets, i.e. Labeled Face Parts in the Wild (LFPW), Helen, EURECOM and AR databases, to demonstrate its robustness and capabilities.
Tasks
Published	2016-07-03
URL	http://arxiv.org/abs/1607.00659v1
PDF	http://arxiv.org/pdf/1607.00659v1.pdf
PWC	https://paperswithcode.com/paper/robust-deep-appearance-models
Repo
Framework

Unsupervised clustering under the Union of Polyhedral Cones (UOPC) model


Title	Unsupervised clustering under the Union of Polyhedral Cones (UOPC) model
Authors	Wenqi Wang, Vaneet Aggarwal, Shuchin Aeron
Abstract	In this paper, we consider clustering data that is assumed to come from one of finitely many pointed convex polyhedral cones. This model is referred to as the Union of Polyhedral Cones (UOPC) model. Similar to the Union of Subspaces (UOS) model where each data from each subspace is generated from a (unknown) basis, in the UOPC model each data from each cone is assumed to be generated from a finite number of (unknown) \emph{extreme rays}.To cluster data under this model, we consider several algorithms - (a) Sparse Subspace Clustering by Non-negative constraints Lasso (NCL), (b) Least squares approximation (LSA), and (c) K-nearest neighbor (KNN) algorithm to arrive at affinity between data points. Spectral Clustering (SC) is then applied on the resulting affinity matrix to cluster data into different polyhedral cones. We show that on an average KNN outperforms both NCL and LSA and for this algorithm we provide the deterministic conditions for correct clustering. For an affinity measure between the cones it is shown that as long as the cones are not very coherent and as long as the density of data within each cone exceeds a threshold, KNN leads to accurate clustering. Finally, simulation results on real datasets (MNIST and YaleFace datasets) depict that the proposed algorithm works well on real data indicating the utility of the UOPC model and the proposed algorithm.
Tasks
Published	2016-10-15
URL	http://arxiv.org/abs/1610.04751v1
PDF	http://arxiv.org/pdf/1610.04751v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-clustering-under-the-union-of
Repo
Framework

Deep Learning and Hierarchal Generative Models


Title	Deep Learning and Hierarchal Generative Models
Authors	Elchanan Mossel
Abstract	It is argued that deep learning is efficient for data that is generated from hierarchal generative models. Examples of such generative models include wavelet scattering networks, functions of compositional structure, and deep rendering models. Unfortunately so far, for all such models, it is either not rigorously known that they can be learned efficiently, or it is not known that “deep algorithms” are required in order to learn them. We propose a simple family of “generative hierarchal models” which can be efficiently learned and where “deep” algorithm are necessary for learning. Our definition of “deep” algorithms is based on the empirical observation that deep nets necessarily use correlations between features. More formally, we show that in a semi-supervised setting, given access to low-order moments of the labeled data and all of the unlabeled data, it is information theoretically impossible to perform classification while at the same time there is an efficient algorithm, that given all labelled and unlabeled data, perfectly labels all unlabelled data with high probability. For the proof, we use and strengthen the fact that Belief Propagation does not admit a good approximation in terms of linear functions.
Tasks
Published	2016-12-29
URL	http://arxiv.org/abs/1612.09057v4
PDF	http://arxiv.org/pdf/1612.09057v4.pdf
PWC	https://paperswithcode.com/paper/deep-learning-and-hierarchal-generative
Repo
Framework

End-to-End Eye Movement Detection Using Convolutional Neural Networks


Title	End-to-End Eye Movement Detection Using Convolutional Neural Networks
Authors	Sabrina Hoppe, Andreas Bulling
Abstract	Common computational methods for automated eye movement detection - i.e. the task of detecting different types of eye movement in a continuous stream of gaze data - are limited in that they either involve thresholding on hand-crafted signal features, require individual detectors each only detecting a single movement, or require pre-segmented data. We propose a novel approach for eye movement detection that only involves learning a single detector end-to-end, i.e. directly from the continuous gaze data stream and simultaneously for different eye movements without any manual feature crafting or segmentation. Our method is based on convolutional neural networks (CNN) that recently demonstrated superior performance in a variety of tasks in computer vision, signal processing, and machine learning. We further introduce a novel multi-participant dataset that contains scripted and free-viewing sequences of ground-truth annotated saccades, fixations, and smooth pursuits. We show that our CNN-based method outperforms state-of-the-art baselines by a large margin on this challenging dataset, thereby underlining the significant potential of this approach for holistic, robust, and accurate eye movement protocol analysis.
Tasks
Published	2016-09-08
URL	http://arxiv.org/abs/1609.02452v1
PDF	http://arxiv.org/pdf/1609.02452v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-eye-movement-detection-using
Repo
Framework

Exploring Implicit Human Responses to Robot Mistakes in a Learning from Demonstration Task


Title	Exploring Implicit Human Responses to Robot Mistakes in a Learning from Demonstration Task
Authors	Cory J. Hayes, Maryam Moosaei, Laurel D. Riek
Abstract	As robots enter human environments, they will be expected to accomplish a tremendous range of tasks. It is not feasible for robot designers to pre-program these behaviors or know them in advance, so one way to address this is through end-user programming, such as via learning from demonstration (LfD). While significant work has been done on the mechanics of enabling robot learning from human teachers, one unexplored aspect is enabling mutual feedback between both the human teacher and robot during the learning process, i.e., implicit learning. In this paper, we explore one aspect of this mutual understanding, grounding sequences, where both a human and robot provide non-verbal feedback to signify their mutual understanding during interaction. We conducted a study where people taught an autonomous humanoid robot a dance, and performed gesture analysis to measure people’s responses to the robot during correct and incorrect demonstrations.
Tasks
Published	2016-06-08
URL	http://arxiv.org/abs/1606.02485v1
PDF	http://arxiv.org/pdf/1606.02485v1.pdf
PWC	https://paperswithcode.com/paper/exploring-implicit-human-responses-to-robot
Repo
Framework